Building on the topics covered in ML fundamentals module, the Finance module will continue and cover the following topics:

• Statistical / probabilistic ML (e.g., Bayesian ML, Gaussian processes, approximate inference, modelling uncertainty, learning from large data, ...)

• Advanced topics in representation learning (e.g., learning with no labels, representation learning in time series, text, and multi-modal data)

• Natural language processing (e.g., large language models, multi-lingual NLP, sentiment/opinion mining, fact checking / false news, misinformation detection, ...)

• Reinforcement learning

• Knowledge graphs

• Knowledge-aware ML

• Symbolic reasoning

• Neuro-symbolic AI

Applied talks on ML in/for:

• Financial time series (e.g., standard models, Gaussian processes, representation learning, ...)

• Building market simulators

• Trading and hedging

• Insurance, asset management, emerging risks

• Financial inclusion and economic prosperity

• ESG

• ...

• Taking ML to the real-world settings (e.g., interpretability, ethics, ML Ops, ML products, ...)

• And more